Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 43101
    Prev
    Next
    INDEX
    Explanations

    black holes and gravity waves

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     distancing
    -0.08
     조
    -0.08
    relu
    -0.08
     experimentation
    -0.07
    조
    -0.07
    perimental
    -0.07
     skepticism
    -0.07
     defence
    -0.07
     socioeconomic
    -0.07
     scept
    -0.07
    POSITIVE LOGITS
     เว็บไซต์
    0.08
    raquo
    0.08
     وسوف
    0.08
    ుష
    0.08
     gider
    0.08
     бан
    0.08
     أك
    0.08
    keiten
    0.08
     kwi
    0.08
     péd
    0.08
    Activations Density 0.001%

    No Known Activations